Exit Menu

Horoscopic 3D Vision

Funding body


 

Project description

Holoscopic 3D imaging (also known as Integral imaging) is a promising technique for capturing full colour 3D images using a single aperture camera. It mimics fly’s eye technique, which records true 3D optical model of the scene onto two-dimensional surface. Holoscopic 3D camera provides enrich and scalable digital images to carry out multi-layer 3D measurement, 3D depth sensing, 3D reconstruction as well as creation of multi-format 3D images and this makes an optimum candidate for autonomous systems and robotics unlike any other passive 3D sensors such as Stereoscopic 3D cameras has a complex setup and provides a fixed based line which limits the depth. Holoscopic 3D camera lens adaptors can be done to any existing 2D cameras and At Brunel, we developed innovative scalable holoscopic 3D pixel mapping method which enables to make HD holoscopic 3D camera sensor using available 2D sensor therefore it offers a low-cost and sustainable solutions for complex and dynamic problems.

The following aspects of Autonomous navigation are currently under investigation. The use of monocular vision to control autonomous navigation for a robot in a dynamically changing environment has been explored. Moreover, this approach is under investigation to replicate flocking behaviour with artificial systems.

At the same time, to facilitate the human robot interaction, a novel approach exploring the use of microblogging to manage interaction between humans and robots has been developed at Brunel University. The approach uses Natural Language Processing to extract features of interest from textual data retrieved from a microblogging platform in real-time and generate appropriate executable code for the robot. The solution exploits some of the ‘natural’ constraints imposed by microblogging platforms to manage the potential complexity of the interactions and create bi-directional communication.

Initial tests demonstrates the feasibility of producing programmes from the social media data which lead to executable actions by a front-end application.

Finally, theoretical work on how gender differences arise in navigation and interactive communication with computer systems has been explored.